Merge tag 'for-5.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Features, highlights:

   - async discard
       - "mount -o discard=async" to enable it
       - freed extents are not discarded immediatelly, but grouped
         together and trimmed later, with IO rate limiting
       - the "sync" mode submits short extents that could have been
         ignored completely by the device, for SATA prior to 3.1 the
         requests are unqueued and have a big impact on performance
       - the actual discard IO requests have been moved out of
         transaction commit to a worker thread, improving commit latency
       - IO rate and request size can be tuned by sysfs files, for now
         enabled only with CONFIG_BTRFS_DEBUG as we might need to
         add/delete the files and don't have a stable-ish ABI for
         general use, defaults are conservative

   - export device state info in sysfs, eg. missing, writeable

   - no discard of extents known to be untouched on disk (eg. after
     reservation)

   - device stats reset is logged with process name and PID that called
     the ioctl

  Fixes:

   - fix missing hole after hole punching and fsync when using NO_HOLES

   - writeback: range cyclic mode could miss some dirty pages and lead
     to OOM

   - two more corner cases for metadata_uuid change after power loss
     during the change

   - fix infinite loop during fsync after mix of rename operations

  Core changes:

   - qgroup assign returns ENOTCONN when quotas not enabled, used to
     return EINVAL that was confusing

   - device closing does not need to allocate memory anymore

   - snapshot aware code got removed, disabled for years due to
     performance problems, reimplmentation will allow to select wheter
     defrag breaks or does not break COW on shared extents

   - tree-checker:
       - check leaf chunk item size, cross check against number of
         stripes
       - verify location keys for DIR_ITEM, DIR_INDEX and XATTR items

   - new self test for physical -> logical mapping code, used for super
     block range exclusion

   - assertion helpers/macros updated to avoid objtool "unreachable
     code" reports on older compilers or config option combinations"

* tag 'for-5.6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (84 commits)
  btrfs: free block groups after free'ing fs trees
  btrfs: Fix split-brain handling when changing FSID to metadata uuid
  btrfs: Handle another split brain scenario with metadata uuid feature
  btrfs: Factor out metadata_uuid code from find_fsid.
  btrfs: Call find_fsid from find_fsid_inprogress
  Btrfs: fix infinite loop during fsync after rename operations
  btrfs: set trans->drity in btrfs_commit_transaction
  btrfs: drop log root for dropped roots
  btrfs: sysfs, add devid/dev_state kobject and device attributes
  btrfs: Refactor btrfs_rmap_block to improve readability
  btrfs: Add self-tests for btrfs_rmap_block
  btrfs: selftests: Add support for dummy devices
  btrfs: Move and unexport btrfs_rmap_block
  btrfs: separate definition of assertion failure handlers
  btrfs: device stats, log when stats are zeroed
  btrfs: fix improper setting of scanned for range cyclic write cache pages
  btrfs: safely advance counter when looking up bio csums
  btrfs: remove unused member btrfs_device::work
  btrfs: remove unnecessary wrapper get_alloc_profile
  btrfs: add correction to handle -1 edge case in async discard
  ...

fs/btrfs/Makefile

@@ -11,7 +11,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
-	   block-rsv.o delalloc-space.o block-group.o
+	   block-rsv.o delalloc-space.o block-group.o discard.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o

fs/btrfs/block-group.c

@@ -14,6 +14,8 @@
 #include "sysfs.h"
 #include "tree-log.h"
 #include "delalloc-space.h"
+#include "discard.h"
+#include "raid56.h"
 
 /*
  * Return target flags in extended format or 0 if restripe for this chunk_type
@@ -95,7 +97,7 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags)
 	return extended_to_chunk(flags | allowed);
 }
 
-static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
+u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
 {
 	unsigned seq;
 	u64 flags;
@@ -115,11 +117,6 @@ static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
 	return btrfs_reduce_alloc_profile(fs_info, flags);
 }
 
-u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
-{
-	return get_alloc_profile(fs_info, orig_flags);
-}
-
 void btrfs_get_block_group(struct btrfs_block_group *cache)
 {
 	atomic_inc(&cache->count);
@@ -131,6 +128,15 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
 		WARN_ON(cache->pinned > 0);
 		WARN_ON(cache->reserved > 0);
 
+		/*
+		 * A block_group shouldn't be on the discard_list anymore.
+		 * Remove the block_group from the discard_list to prevent us
+		 * from causing a panic due to NULL pointer dereference.
+		 */
+		if (WARN_ON(!list_empty(&cache->discard_list)))
+			btrfs_discard_cancel_work(&cache->fs_info->discard_ctl,
+						  cache);
+
 		/*
 		 * If not empty, someone is still holding mutex of
 		 * full_stripe_lock, which can only be released by caller.
@@ -466,8 +472,8 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
 		} else if (extent_start > start && extent_start < end) {
 			size = extent_start - start;
 			total_added += size;
-			ret = btrfs_add_free_space(block_group, start,
-						   size);
+			ret = btrfs_add_free_space_async_trimmed(block_group,
+								 start, size);
 			BUG_ON(ret); /* -ENOMEM or logic error */
 			start = extent_end + 1;
 		} else {
@@ -478,7 +484,8 @@ u64 add_new_free_space(struct btrfs_block_group *block_group, u64 start, u64 end
 	if (start < end) {
 		size = end - start;
 		total_added += size;
-		ret = btrfs_add_free_space(block_group, start, size);
+		ret = btrfs_add_free_space_async_trimmed(block_group, start,
+							 size);
 		BUG_ON(ret); /* -ENOMEM or logic error */
 	}
 
@@ -1185,21 +1192,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
 	u64 sinfo_used;
-	u64 min_allocable_bytes;
 	int ret = -ENOSPC;
 
-	/*
-	 * We need some metadata space and system metadata space for
-	 * allocating chunks in some corner cases until we force to set
-	 * it to be readonly.
-	 */
-	if ((sinfo->flags &
-	     (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA)) &&
-	    !force)
-		min_allocable_bytes = SZ_1M;
-	else
-		min_allocable_bytes = 0;
-
 	spin_lock(&sinfo->lock);
 	spin_lock(&cache->lock);
 
@@ -1217,10 +1211,9 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 	 * sinfo_used + num_bytes should always <= sinfo->total_bytes.
 	 *
 	 * Here we make sure if we mark this bg RO, we still have enough
-	 * free space as buffer (if min_allocable_bytes is not 0).
+	 * free space as buffer.
 	 */
-	if (sinfo_used + num_bytes + min_allocable_bytes <=
-	    sinfo->total_bytes) {
+	if (sinfo_used + num_bytes <= sinfo->total_bytes) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
@@ -1233,8 +1226,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 		btrfs_info(cache->fs_info,
 			"unable to make block group %llu ro", cache->start);
 		btrfs_info(cache->fs_info,
-			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
-			sinfo_used, num_bytes, min_allocable_bytes);
+			"sinfo_used=%llu bg_num_bytes=%llu",
+			sinfo_used, num_bytes);
 		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
 	}
 	return ret;
@@ -1249,6 +1242,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
+	const bool async_trim_enabled = btrfs_test_opt(fs_info, DISCARD_ASYNC);
 	int ret = 0;
 
 	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
@@ -1272,10 +1266,28 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		}
 		spin_unlock(&fs_info->unused_bgs_lock);
 
+		btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group);
+
 		mutex_lock(&fs_info->delete_unused_bgs_mutex);
 
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
+
+		/*
+		 * Async discard moves the final block group discard to be prior
+		 * to the unused_bgs code path.  Therefore, if it's not fully
+		 * trimmed, punt it back to the async discard lists.
+		 */
+		if (btrfs_test_opt(fs_info, DISCARD_ASYNC) &&
+		    !btrfs_is_free_space_trimmed(block_group)) {
+			trace_btrfs_skip_unused_block_group(block_group);
+			up_write(&space_info->groups_sem);
+			/* Requeue if we failed because of async discard */
+			btrfs_discard_queue_work(&fs_info->discard_ctl,
+						 block_group);
+			goto next;
+		}
+
 		spin_lock(&block_group->lock);
 		if (block_group->reserved || block_group->pinned ||
 		    block_group->used || block_group->ro ||
@@ -1347,6 +1359,23 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		}
 		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 
+		/*
+		 * At this point, the block_group is read only and should fail
+		 * new allocations.  However, btrfs_finish_extent_commit() can
+		 * cause this block_group to be placed back on the discard
+		 * lists because now the block_group isn't fully discarded.
+		 * Bail here and try again later after discarding everything.
+		 */
+		spin_lock(&fs_info->discard_ctl.lock);
+		if (!list_empty(&block_group->discard_list)) {
+			spin_unlock(&fs_info->discard_ctl.lock);
+			btrfs_dec_block_group_ro(block_group);
+			btrfs_discard_queue_work(&fs_info->discard_ctl,
+						 block_group);
+			goto end_trans;
+		}
+		spin_unlock(&fs_info->discard_ctl.lock);
+
 		/* Reset pinned so btrfs_put_block_group doesn't complain */
 		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
@@ -1362,8 +1391,18 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		spin_unlock(&block_group->lock);
 		spin_unlock(&space_info->lock);
 
+		/*
+		 * The normal path here is an unused block group is passed here,
+		 * then trimming is handled in the transaction commit path.
+		 * Async discard interposes before this to do the trimming
+		 * before coming down the unused block group path as trimming
+		 * will no longer be done later in the transaction commit path.
+		 */
+		if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC))
+			goto flip_async;
+
 		/* DISCARD can flip during remount */
-		trimming = btrfs_test_opt(fs_info, DISCARD);
+		trimming = btrfs_test_opt(fs_info, DISCARD_SYNC);
 
 		/* Implicit trim during transaction commit. */
 		if (trimming)
@@ -1406,6 +1445,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
+	return;
+
+flip_async:
+	btrfs_end_transaction(trans);
+	mutex_unlock(&fs_info->delete_unused_bgs_mutex);
+	btrfs_put_block_group(block_group);
+	btrfs_discard_punt_unused_bgs_list(fs_info);
 }
 
 void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
@@ -1516,6 +1562,102 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 	write_sequnlock(&fs_info->profiles_lock);
 }
 
+/**
+ * btrfs_rmap_block - Map a physical disk address to a list of logical addresses
+ * @chunk_start:   logical address of block group
+ * @physical:	   physical address to map to logical addresses
+ * @logical:	   return array of logical addresses which map to @physical
+ * @naddrs:	   length of @logical
+ * @stripe_len:    size of IO stripe for the given block group
+ *
+ * Maps a particular @physical disk address to a list of @logical addresses.
+ * Used primarily to exclude those portions of a block group that contain super
+ * block copies.
+ */
+EXPORT_FOR_TESTS
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
+{
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 *buf;
+	u64 bytenr;
+	u64 data_stripe_length;
+	u64 io_stripe_size;
+	int i, nr = 0;
+	int ret = 0;
+
+	em = btrfs_get_chunk_map(fs_info, chunk_start, 1);
+	if (IS_ERR(em))
+		return -EIO;
+
+	map = em->map_lookup;
+	data_stripe_length = em->len;
+	io_stripe_size = map->stripe_len;
+
+	if (map->type & BTRFS_BLOCK_GROUP_RAID10)
+		data_stripe_length = div_u64(data_stripe_length,
+					     map->num_stripes / map->sub_stripes);
+	else if (map->type & BTRFS_BLOCK_GROUP_RAID0)
+		data_stripe_length = div_u64(data_stripe_length, map->num_stripes);
+	else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		data_stripe_length = div_u64(data_stripe_length,
+					     nr_data_stripes(map));
+		io_stripe_size = map->stripe_len * nr_data_stripes(map);
+	}
+
+	buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		bool already_inserted = false;
+		u64 stripe_nr;
+		int j;
+
+		if (!in_range(physical, map->stripes[i].physical,
+			      data_stripe_length))
+			continue;
+
+		stripe_nr = physical - map->stripes[i].physical;
+		stripe_nr = div64_u64(stripe_nr, map->stripe_len);
+
+		if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
+			stripe_nr = stripe_nr * map->num_stripes + i;
+			stripe_nr = div_u64(stripe_nr, map->sub_stripes);
+		} else if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+			stripe_nr = stripe_nr * map->num_stripes + i;
+		}
+		/*
+		 * The remaining case would be for RAID56, multiply by
+		 * nr_data_stripes().  Alternatively, just use rmap_len below
+		 * instead of map->stripe_len
+		 */
+
+		bytenr = chunk_start + stripe_nr * io_stripe_size;
+
+		/* Ensure we don't add duplicate addresses */
+		for (j = 0; j < nr; j++) {
+			if (buf[j] == bytenr) {
+				already_inserted = true;
+				break;
+			}
+		}
+
+		if (!already_inserted)
+			buf[nr++] = bytenr;
+	}
+
+	*logical = buf;
+	*naddrs = nr;
+	*stripe_len = io_stripe_size;
+out:
+	free_extent_map(em);
+	return ret;
+}
+
 static int exclude_super_stripes(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -1610,6 +1752,8 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
 	set_free_space_tree_thresholds(cache);
 
+	cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED;
+
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
 	init_rwsem(&cache->data_rwsem);
@@ -1617,6 +1761,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 	INIT_LIST_HEAD(&cache->cluster_list);
 	INIT_LIST_HEAD(&cache->bg_list);
 	INIT_LIST_HEAD(&cache->ro_list);
+	INIT_LIST_HEAD(&cache->discard_list);
 	INIT_LIST_HEAD(&cache->dirty_list);
 	INIT_LIST_HEAD(&cache->io_list);
 	btrfs_init_free_space_ctl(cache);
@@ -1775,7 +1920,10 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 		inc_block_group_ro(cache, 1);
 	} else if (cache->used == 0) {
 		ASSERT(list_empty(&cache->bg_list));
-		btrfs_mark_bg_unused(cache);
+		if (btrfs_test_opt(info, DISCARD_ASYNC))
+			btrfs_discard_queue_work(&info->discard_ctl, cache);
+		else
+			btrfs_mark_bg_unused(cache);
 	}
 	return 0;
 error:
@@ -2738,8 +2886,10 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * dirty list to avoid races between cleaner kthread and space
 		 * cache writeout.
 		 */
-		if (!alloc && old_val == 0)
-			btrfs_mark_bg_unused(cache);
+		if (!alloc && old_val == 0) {
+			if (!btrfs_test_opt(info, DISCARD_ASYNC))
+				btrfs_mark_bg_unused(cache);
+		}
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;

fs/btrfs/block-group.h

@@ -12,6 +12,19 @@ enum btrfs_disk_cache_state {
 	BTRFS_DC_SETUP,
 };
 
+/*
+ * This describes the state of the block_group for async discard.  This is due
+ * to the two pass nature of it where extent discarding is prioritized over
+ * bitmap discarding.  BTRFS_DISCARD_RESET_CURSOR is set when we are resetting
+ * between lists to prevent contention for discard state variables
+ * (eg. discard_cursor).
+ */
+enum btrfs_discard_state {
+	BTRFS_DISCARD_EXTENTS,
+	BTRFS_DISCARD_BITMAPS,
+	BTRFS_DISCARD_RESET_CURSOR,
+};
+
 /*
  * Control flags for do_chunk_alloc's force field CHUNK_ALLOC_NO_FORCE means to
  * only allocate a chunk if we really need one.
@@ -116,7 +129,13 @@ struct btrfs_block_group {
 	/* For read-only block groups */
 	struct list_head ro_list;
 
+	/* For discard operations */
 	atomic_t trimming;
+	struct list_head discard_list;
+	int discard_index;
+	u64 discard_eligible_time;
+	u64 discard_cursor;
+	enum btrfs_discard_state discard_state;
 
 	/* For dirty block groups */
 	struct list_head dirty_list;
@@ -158,6 +177,22 @@ struct btrfs_block_group {
 	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
 };
 
+static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
+{
+	return (block_group->start + block_group->length);
+}
+
+static inline bool btrfs_is_block_group_data_only(
+					struct btrfs_block_group *block_group)
+{
+	/*
+	 * In mixed mode the fragmentation is expected to be high, lowering the
+	 * efficiency, so only proper data block groups are considered.
+	 */
+	return (block_group->flags & BTRFS_BLOCK_GROUP_DATA) &&
+	       !(block_group->flags & BTRFS_BLOCK_GROUP_METADATA);
+}
+
 #ifdef CONFIG_BTRFS_DEBUG
 static inline int btrfs_should_fragment_free_space(
 		struct btrfs_block_group *block_group)
@@ -248,4 +283,9 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
 		cache->cached == BTRFS_CACHE_ERROR;
 }
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
+#endif
+
 #endif /* BTRFS_BLOCK_GROUP_H */

fs/btrfs/check-integrity.c

@@ -629,7 +629,6 @@ static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev,
 static int btrfsic_process_superblock(struct btrfsic_state *state,
 				      struct btrfs_fs_devices *fs_devices)
 {
-	struct btrfs_fs_info *fs_info = state->fs_info;
 	struct btrfs_super_block *selected_super;
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
@@ -637,7 +636,6 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 	int ret = 0;
 	int pass;
 
-	BUG_ON(NULL == state);
 	selected_super = kzalloc(sizeof(*selected_super), GFP_NOFS);
 	if (NULL == selected_super) {
 		pr_info("btrfsic: error, kmalloc failed!\n");
@@ -700,7 +698,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 			break;
 		}
 
-		num_copies = btrfs_num_copies(fs_info, next_bytenr,
+		num_copies = btrfs_num_copies(state->fs_info, next_bytenr,
 					      state->metablock_size);
 		if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES)
 			pr_info("num_copies(log_bytenr=%llu) = %d\n",

fs/btrfs/compression.c

@@ -763,7 +763,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
 				ret = btrfs_lookup_bio_sums(inode, comp_bio,
-							    sums);
+							    (u64)-1, sums);
 				BUG_ON(ret); /* -ENOMEM */
 			}
 
@@ -791,7 +791,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	BUG_ON(ret); /* -ENOMEM */
 
 	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-		ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
+		ret = btrfs_lookup_bio_sums(inode, comp_bio, (u64)-1, sums);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 

fs/btrfs/ctree.h

@@ -101,6 +101,14 @@ struct btrfs_ref;
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
+/*
+ * Deltas are an effective way to populate global statistics.  Give macro names
+ * to make it clear what we're doing.  An example is discard_extents in
+ * btrfs_free_space_ctl.
+ */
+#define BTRFS_STAT_NR_ENTRIES	2
+#define BTRFS_STAT_CURR		0
+#define BTRFS_STAT_PREV		1
 
 /*
  * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
@@ -440,6 +448,36 @@ struct btrfs_full_stripe_locks_tree {
 	struct mutex lock;
 };
 
+/* Discard control. */
+/*
+ * Async discard uses multiple lists to differentiate the discard filter
+ * parameters.  Index 0 is for completely free block groups where we need to
+ * ensure the entire block group is trimmed without being lossy.  Indices
+ * afterwards represent monotonically decreasing discard filter sizes to
+ * prioritize what should be discarded next.
+ */
+#define BTRFS_NR_DISCARD_LISTS		3
+#define BTRFS_DISCARD_INDEX_UNUSED	0
+#define BTRFS_DISCARD_INDEX_START	1
+
+struct btrfs_discard_ctl {
+	struct workqueue_struct *discard_workers;
+	struct delayed_work work;
+	spinlock_t lock;
+	struct btrfs_block_group *block_group;
+	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
+	u64 prev_discard;
+	atomic_t discardable_extents;
+	atomic64_t discardable_bytes;
+	u64 max_discard_size;
+	unsigned long delay;
+	u32 iops_limit;
+	u32 kbps_limit;
+	u64 discard_extent_bytes;
+	u64 discard_bitmap_bytes;
+	atomic64_t discard_bytes_saved;
+};
+
 /* delayed seq elem */
 struct seq_list {
 	struct list_head list;
@@ -526,6 +564,9 @@ enum {
 	 * so we don't need to offload checksums to workqueues.
 	 */
 	BTRFS_FS_CSUM_IMPL_FAST,
+
+	/* Indicate that the discard workqueue can service discards. */
+	BTRFS_FS_DISCARD_RUNNING,
 };
 
 struct btrfs_fs_info {
@@ -816,6 +857,8 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *scrub_wr_completion_workers;
 	struct btrfs_workqueue *scrub_parity_workers;
 
+	struct btrfs_discard_ctl discard_ctl;
+
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	u32 check_integrity_print_mask;
 #endif
@@ -902,6 +945,11 @@ struct btrfs_fs_info {
 	spinlock_t ref_verify_lock;
 	struct rb_root block_tree;
 #endif
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct kobject *debug_kobj;
+	struct kobject *discard_debug_kobj;
+#endif
 };
 
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
@@ -1170,7 +1218,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_FLUSHONCOMMIT       (1 << 7)
 #define BTRFS_MOUNT_SSD_SPREAD		(1 << 8)
 #define BTRFS_MOUNT_NOSSD		(1 << 9)
-#define BTRFS_MOUNT_DISCARD		(1 << 10)
+#define BTRFS_MOUNT_DISCARD_SYNC	(1 << 10)
 #define BTRFS_MOUNT_FORCE_COMPRESS      (1 << 11)
 #define BTRFS_MOUNT_SPACE_CACHE		(1 << 12)
 #define BTRFS_MOUNT_CLEAR_CACHE		(1 << 13)
@@ -1189,6 +1237,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_FREE_SPACE_TREE	(1 << 26)
 #define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 #define BTRFS_MOUNT_REF_VERIFY		(1 << 28)
+#define BTRFS_MOUNT_DISCARD_ASYNC	(1 << 29)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)
@@ -2449,8 +2498,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);
 
 int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 			       u64 start, u64 len, int delalloc);
-int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
-				       u64 start, u64 len);
+int btrfs_pin_reserved_extent(struct btrfs_fs_info *fs_info, u64 start,
+			      u64 len);
 void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
@@ -2789,9 +2838,7 @@ struct btrfs_dio_private;
 int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, u64 bytenr, u64 len);
 blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
-				   u8 *dst);
-blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio,
-			      u64 logical_offset);
+				   u64 offset, u8 *dst);
 int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     u64 objectid, u64 pos,
@@ -2877,7 +2924,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root);
 struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
-				    u64 start, u64 end, int create);
+				    u64 start, u64 end);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct inode *inode);
@@ -3110,17 +3157,21 @@ do {								\
 	rcu_read_unlock();					\
 } while (0)
 
-__cold
-static inline void assfail(const char *expr, const char *file, int line)
+#ifdef CONFIG_BTRFS_ASSERT
+__cold __noreturn
+static inline void assertfail(const char *expr, const char *file, int line)
 {
-	if (IS_ENABLED(CONFIG_BTRFS_ASSERT)) {
-		pr_err("assertion failed: %s, in %s:%d\n", expr, file, line);
-		BUG();
-	}
+	pr_err("assertion failed: %s, in %s:%d\n", expr, file, line);
+	BUG();
 }
 
-#define ASSERT(expr)	\
-	(likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+#define ASSERT(expr)						\
+	(likely(expr) ? (void)0 : assertfail(#expr, __FILE__, __LINE__))
+
+#else
+static inline void assertfail(const char *expr, const char* file, int line) { }
+#define ASSERT(expr)	(void)(expr)
+#endif
 
 /*
  * Use that for functions that are conditionally exported for sanity tests but

fs/btrfs/dev-replace.c

@@ -704,6 +704,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	/* replace the sysfs entry */
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device);
+	btrfs_sysfs_update_devid(tgt_device);
 	btrfs_rm_dev_replace_free_srcdev(src_device);
 
 	/* write back the superblocks */

fs/btrfs/discard.h

+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef BTRFS_DISCARD_H
+#define BTRFS_DISCARD_H
+
+#include <linux/sizes.h>
+
+struct btrfs_fs_info;
+struct btrfs_discard_ctl;
+struct btrfs_block_group;
+
+/* Discard size limits */
+#define BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE		(SZ_64M)
+#define BTRFS_ASYNC_DISCARD_MAX_FILTER			(SZ_1M)
+#define BTRFS_ASYNC_DISCARD_MIN_FILTER			(SZ_32K)
+
+/* List operations */
+void btrfs_discard_check_filter(struct btrfs_block_group *block_group, u64 bytes);
+
+/* Work operations */
+void btrfs_discard_cancel_work(struct btrfs_discard_ctl *discard_ctl,
+			       struct btrfs_block_group *block_group);
+void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl,
+			      struct btrfs_block_group *block_group);
+void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+				 bool override);
+bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
+
+/* Update operations */
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);
+void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
+				      struct btrfs_free_space_ctl *ctl);
+
+/* Setup/cleanup operations */
+void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info);
+void btrfs_discard_resume(struct btrfs_fs_info *fs_info);
+void btrfs_discard_stop(struct btrfs_fs_info *fs_info);
+void btrfs_discard_init(struct btrfs_fs_info *fs_info);
+void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info);
+
+#endif

fs/btrfs/disk-io.c

@@ -41,6 +41,7 @@
 #include "tree-checker.h"
 #include "ref-verify.h"
 #include "block-group.h"
+#include "discard.h"
 
 #define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
 				 BTRFS_HEADER_FLAG_RELOC |\
@@ -202,8 +203,8 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
  * that covers the entire device
  */
 struct extent_map *btree_get_extent(struct btrfs_inode *inode,
-		struct page *page, size_t pg_offset, u64 start, u64 len,
-		int create)
+				    struct page *page, size_t pg_offset,
+				    u64 start, u64 len)
 {
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
@@ -1953,6 +1954,8 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->readahead_workers);
 	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
+	if (fs_info->discard_ctl.discard_workers)
+		destroy_workqueue(fs_info->discard_ctl.discard_workers);
 	/*
 	 * Now that all other work queues are destroyed, we can safely destroy
 	 * the queues used for metadata I/O, since tasks from those other work
@@ -2148,6 +2151,8 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 				      max_active, 2);
 	fs_info->qgroup_rescan_workers =
 		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
+	fs_info->discard_ctl.discard_workers =
+		alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1);
 
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
 	      fs_info->flush_workers &&
@@ -2158,7 +2163,8 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->readahead_workers &&
 	      fs_info->fixup_workers && fs_info->delayed_workers &&
-	      fs_info->qgroup_rescan_workers)) {
+	      fs_info->qgroup_rescan_workers &&
+	      fs_info->discard_ctl.discard_workers)) {
 		return -ENOMEM;
 	}
 
@@ -2792,6 +2798,7 @@ int __cold open_ctree(struct super_block *sb,
 
 	btrfs_init_dev_replace_locks(fs_info);
 	btrfs_init_qgroup(fs_info);
+	btrfs_discard_init(fs_info);
 
 	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
 	btrfs_init_free_cluster(&fs_info->data_alloc_cluster);
@@ -3082,20 +3089,13 @@ int __cold open_ctree(struct super_block *sb,
 
 	btrfs_free_extra_devids(fs_devices, 1);
 
-	ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
+	ret = btrfs_sysfs_add_fsid(fs_devices);
 	if (ret) {
 		btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
 				ret);
 		goto fail_block_groups;
 	}
 
-	ret = btrfs_sysfs_add_device(fs_devices);
-	if (ret) {
-		btrfs_err(fs_info, "failed to init sysfs device interface: %d",
-				ret);
-		goto fail_fsdev_sysfs;
-	}
-
 	ret = btrfs_sysfs_add_mounted(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
@@ -3262,6 +3262,7 @@ int __cold open_ctree(struct super_block *sb,
 	}
 
 	btrfs_qgroup_rescan_resume(fs_info);
+	btrfs_discard_resume(fs_info);
 
 	if (!fs_info->uuid_root) {
 		btrfs_info(fs_info, "creating UUID tree");
@@ -3978,6 +3979,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
 
+	/* Cancel or finish ongoing discard work */
+	btrfs_discard_cleanup(fs_info);
+
 	if (!sb_rdonly(fs_info->sb)) {
 		/*
 		 * The cleaner kthread is stopped, so do one final pass over
@@ -4026,11 +4030,18 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, true);
 
+	/*
+	 * We must free the block groups after dropping the fs_roots as we could
+	 * have had an IO error and have left over tree log blocks that aren't
+	 * cleaned up until the fs roots are freed.  This makes the block group
+	 * accounting appear to be wrong because there's pending reserved bytes,
+	 * so make sure we do the block group cleanup afterwards.
+	 */
+	btrfs_free_block_groups(fs_info);
+
 	iput(fs_info->btree_inode);
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY

fs/btrfs/disk-io.h

@@ -134,8 +134,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 int btree_lock_page_hook(struct page *page, void *data,
 				void (*flush_fn)(void *));
 struct extent_map *btree_get_extent(struct btrfs_inode *inode,
-		struct page *page, size_t pg_offset, u64 start, u64 len,
-		int create);
+				    struct page *page, size_t pg_offset,
+				    u64 start, u64 len);
 int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);

fs/btrfs/extent-tree.c

@@ -32,6 +32,7 @@
 #include "block-rsv.h"
 #include "delalloc-space.h"
 #include "block-group.h"
+#include "discard.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -2923,7 +2924,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 			break;
 		}
 
-		if (btrfs_test_opt(fs_info, DISCARD))
+		if (btrfs_test_opt(fs_info, DISCARD_SYNC))
 			ret = btrfs_discard_extent(fs_info, start,
 						   end + 1 - start, NULL);
 
@@ -2934,6 +2935,11 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 		cond_resched();
 	}
 
+	if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) {
+		btrfs_discard_calc_delay(&fs_info->discard_ctl);
+		btrfs_discard_schedule_work(&fs_info->discard_ctl, true);
+	}
+
 	/*
 	 * Transaction is finished.  We don't need the lock anymore.  We
 	 * do need to clean up the block groups in case of a transaction
@@ -3438,7 +3444,6 @@ btrfs_release_block_group(struct btrfs_block_group *cache,
  */
 struct find_free_extent_ctl {
 	/* Basic allocation info */
-	u64 ram_bytes;
 	u64 num_bytes;
 	u64 empty_size;
 	u64 flags;
@@ -3810,7 +3815,6 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 
 	WARN_ON(num_bytes < fs_info->sectorsize);
 
-	ffe_ctl.ram_bytes = ram_bytes;
 	ffe_ctl.num_bytes = num_bytes;
 	ffe_ctl.empty_size = empty_size;
 	ffe_ctl.flags = flags;
@@ -4165,12 +4169,10 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
 	return ret;
 }
 
-static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
-					u64 start, u64 len,
-					int pin, int delalloc)
+int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
+			       u64 start, u64 len, int delalloc)
 {
 	struct btrfs_block_group *cache;
-	int ret = 0;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
 	if (!cache) {
@@ -4179,30 +4181,28 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 		return -ENOSPC;
 	}
 
-	if (pin)
-		pin_down_extent(cache, start, len, 1);
-	else {
-		if (btrfs_test_opt(fs_info, DISCARD))
-			ret = btrfs_discard_extent(fs_info, start, len, NULL);
-		btrfs_add_free_space(cache, start, len);
-		btrfs_free_reserved_bytes(cache, len, delalloc);
-		trace_btrfs_reserved_extent_free(fs_info, start, len);
-	}
+	btrfs_add_free_space(cache, start, len);
+	btrfs_free_reserved_bytes(cache, len, delalloc);
+	trace_btrfs_reserved_extent_free(fs_info, start, len);
 
 	btrfs_put_block_group(cache);
-	return ret;
+	return 0;
 }
 
-int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
-			       u64 start, u64 len, int delalloc)
+int btrfs_pin_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
 {
-	return __btrfs_free_reserved_extent(fs_info, start, len, 0, delalloc);
-}
+	struct btrfs_block_group *cache;
+	int ret = 0;
 
-int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
-				       u64 start, u64 len)
-{
-	return __btrfs_free_reserved_extent(fs_info, start, len, 1, 0);
+	cache = btrfs_lookup_block_group(fs_info, start);
+	if (!cache) {
+		btrfs_err(fs_info, "unable to find block group for %llu", start);
+		return -ENOSPC;
+	}
+
+	ret = pin_down_extent(cache, start, len, 1);
+	btrfs_put_block_group(cache);
+	return ret;
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,

fs/btrfs/extent_io.c

@@ -3043,7 +3043,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		*em_cached = NULL;
 	}
 
-	em = get_extent(BTRFS_I(inode), page, pg_offset, start, len, 0);
+	em = get_extent(BTRFS_I(inode), page, pg_offset, start, len);
 	if (em_cached && !IS_ERR_OR_NULL(em)) {
 		BUG_ON(*em_cached);
 		refcount_inc(&em->refs);
@@ -3455,11 +3455,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	update_nr_written(wbc, nr_written + 1);
 
 	end = page_end;
-	if (i_size <= start) {
-		btrfs_writepage_endio_finish_ordered(page, start, page_end, 1);
-		goto done;
-	}
-
 	blocksize = inode->i_sb->s_blocksize;
 
 	while (cur <= end) {
@@ -3471,8 +3466,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 							     page_end, 1);
 			break;
 		}
-		em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, cur,
-				     end - cur + 1, 1);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur,
+				      end - cur + 1);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
 			ret = PTR_ERR_OR_ZERO(em);
@@ -3497,22 +3492,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		 */
 		if (compressed || block_start == EXTENT_MAP_HOLE ||
 		    block_start == EXTENT_MAP_INLINE) {
-			/*
-			 * end_io notification does not happen here for
-			 * compressed extents
-			 */
-			if (!compressed)
-				btrfs_writepage_endio_finish_ordered(page, cur,
-							    cur + iosize - 1,
-							    1);
-			else if (compressed) {
-				/* we don't want to end_page_writeback on
-				 * a compressed extent.  this happens
-				 * elsewhere
-				 */
+			if (compressed)
 				nr++;
-			}
-
+			else
+				btrfs_writepage_endio_finish_ordered(page, cur,
+							cur + iosize - 1, 1);
 			cur += iosize;
 			pg_offset += iosize;
 			continue;
@@ -3540,7 +3524,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 		pg_offset += iosize;
 		nr++;
 	}
-done:
 	*nr_ret = nr;
 	return ret;
 }
@@ -3562,7 +3545,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	u64 page_end = start + PAGE_SIZE - 1;
 	int ret;
 	int nr = 0;
-	size_t pg_offset = 0;
+	size_t pg_offset;
 	loff_t i_size = i_size_read(inode);
 	unsigned long end_index = i_size >> PAGE_SHIFT;
 	unsigned long nr_written = 0;
@@ -3591,14 +3574,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		flush_dcache_page(page);
 	}
 
-	pg_offset = 0;
-
 	set_page_extent_mapped(page);
 
 	if (!epd->extent_locked) {
 		ret = writepage_delalloc(inode, page, wbc, start, &nr_written);
 		if (ret == 1)
-			goto done_unlocked;
+			return 0;
 		if (ret)
 			goto done;
 	}
@@ -3606,7 +3587,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	ret = __extent_writepage_io(inode, page, wbc, epd,
 				    i_size, nr_written, &nr);
 	if (ret == 1)
-		goto done_unlocked;
+		return 0;
 
 done:
 	if (nr == 0) {
@@ -3621,9 +3602,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	unlock_page(page);
 	ASSERT(ret <= 0);
 	return ret;
-
-done_unlocked:
-	return 0;
 }
 
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
@@ -3941,6 +3919,11 @@ int btree_write_cache_pages(struct address_space *mapping,
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
@@ -3958,7 +3941,6 @@ int btree_write_cache_pages(struct address_space *mapping,
 			tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
@@ -4087,6 +4069,11 @@ static int extent_write_cache_pages(struct address_space *mapping,
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
+		/*
+		 * Start from the beginning does not need to cycle over the
+		 * range, mark it as scanned.
+		 */
+		scanned = (index == 0);
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
@@ -4120,7 +4107,6 @@ static int extent_write_cache_pages(struct address_space *mapping,
 						&index, end, tag))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 

fs/btrfs/extent_io.h

@@ -183,10 +183,8 @@ static inline int extent_compress_type(unsigned long bio_flags)
 struct extent_map_tree;
 
 typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
-					  struct page *page,
-					  size_t pg_offset,
-					  u64 start, u64 len,
-					  int create);
+					  struct page *page, size_t pg_offset,
+					  u64 start, u64 len);
 
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);

fs/btrfs/file-item.c

@@ -148,8 +148,19 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
-				   u64 logical_offset, u8 *dst, int dio)
+/**
+ * btrfs_lookup_bio_sums - Look up checksums for a bio.
+ * @inode: inode that the bio is for.
+ * @bio: bio embedded in btrfs_io_bio.
+ * @offset: Unless (u64)-1, look up checksums for this offset in the file.
+ *          If (u64)-1, use the page offsets from the bio instead.
+ * @dst: Buffer of size btrfs_super_csum_size() used to return checksum. If
+ *       NULL, the checksum is returned in btrfs_io_bio(bio)->csum instead.
+ *
+ * Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise.
+ */
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
+				   u64 offset, u8 *dst)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct bio_vec bvec;
@@ -158,8 +169,8 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio
 	struct btrfs_csum_item *item = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_path *path;
+	const bool page_offsets = (offset == (u64)-1);
 	u8 *csum;
-	u64 offset = 0;
 	u64 item_start_offset = 0;
 	u64 item_last_offset = 0;
 	u64 disk_bytenr;
@@ -205,15 +216,13 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio
 	}
 
 	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
-	if (dio)
-		offset = logical_offset;
 
 	bio_for_each_segment(bvec, bio, iter) {
 		page_bytes_left = bvec.bv_len;
 		if (count)
 			goto next;
 
-		if (!dio)
+		if (page_offsets)
 			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 		count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
 					       csum, nblocks);
@@ -274,7 +283,8 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio
 		csum += count * csum_size;
 		nblocks -= count;
 next:
-		while (count--) {
+		while (count > 0) {
+			count--;
 			disk_bytenr += fs_info->sectorsize;
 			offset += fs_info->sectorsize;
 			page_bytes_left -= fs_info->sectorsize;
@@ -285,18 +295,7 @@ static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio
 
 	WARN_ON_ONCE(count);
 	btrfs_free_path(path);
-	return 0;
-}
-
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
-				   u8 *dst)
-{
-	return __btrfs_lookup_bio_sums(inode, bio, 0, dst, 0);
-}
-
-blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset)
-{
-	return __btrfs_lookup_bio_sums(inode, bio, offset, NULL, 1);
+	return BLK_STS_OK;
 }
 
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
@@ -483,8 +482,8 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 						 - 1);
 
 		for (i = 0; i < nr_sectors; i++) {
-			if (offset >= ordered->file_offset + ordered->len ||
-				offset < ordered->file_offset) {
+			if (offset >= ordered->file_offset + ordered->num_bytes ||
+			    offset < ordered->file_offset) {
 				unsigned long bytes_left;
 
 				sums->len = this_sum_bytes;

fs/btrfs/file.c

@@ -477,8 +477,7 @@ static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
 		u64 em_len;
 		int ret = 0;
 
-		em = btrfs_get_extent(inode, NULL, 0, search_start,
-				      search_len, 0);
+		em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
 		if (IS_ERR(em))
 			return PTR_ERR(em);
 
@@ -1501,7 +1500,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 		ordered = btrfs_lookup_ordered_range(inode, start_pos,
 						     last_pos - start_pos + 1);
 		if (ordered &&
-		    ordered->file_offset + ordered->len > start_pos &&
+		    ordered->file_offset + ordered->num_bytes > start_pos &&
 		    ordered->file_offset <= last_pos) {
 			unlock_extent_cached(&inode->io_tree, start_pos,
 					last_pos, cached_state);
@@ -2390,7 +2389,7 @@ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
 
 	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
 			      round_down(*start, fs_info->sectorsize),
-			      round_up(*len, fs_info->sectorsize), 0);
+			      round_up(*len, fs_info->sectorsize));
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 
@@ -2426,7 +2425,7 @@ static int btrfs_punch_hole_lock_range(struct inode *inode,
 		 * we need to try again.
 		 */
 		if ((!ordered ||
-		    (ordered->file_offset + ordered->len <= lockstart ||
+		    (ordered->file_offset + ordered->num_bytes <= lockstart ||
 		     ordered->file_offset > lockend)) &&
 		     !filemap_range_has_page(inode->i_mapping,
 					     lockstart, lockend)) {
@@ -2957,7 +2956,7 @@ static int btrfs_zero_range_check_range_boundary(struct inode *inode,
 	int ret;
 
 	offset = round_down(offset, sectorsize);
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize);
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 
@@ -2990,8 +2989,8 @@ static int btrfs_zero_range(struct inode *inode,
 
 	inode_dio_wait(inode);
 
-	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
-			      alloc_start, alloc_end - alloc_start, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
+			      alloc_end - alloc_start);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto out;
@@ -3034,8 +3033,8 @@ static int btrfs_zero_range(struct inode *inode,
 
 	if (BTRFS_BYTES_TO_BLKS(fs_info, offset) ==
 	    BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) {
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
-				      alloc_start, sectorsize, 0);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
+				      sectorsize);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			goto out;
@@ -3248,7 +3247,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		ordered = btrfs_lookup_first_ordered_extent(inode, locked_end);
 
 		if (ordered &&
-		    ordered->file_offset + ordered->len > alloc_start &&
+		    ordered->file_offset + ordered->num_bytes > alloc_start &&
 		    ordered->file_offset < alloc_end) {
 			btrfs_put_ordered_extent(ordered);
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
@@ -3273,7 +3272,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	INIT_LIST_HEAD(&reserve_list);
 	while (cur_offset < alloc_end) {
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
-				      alloc_end - cur_offset, 0);
+				      alloc_end - cur_offset);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			break;

fs/btrfs/free-space-cache.h

@@ -6,6 +6,20 @@
 #ifndef BTRFS_FREE_SPACE_CACHE_H
 #define BTRFS_FREE_SPACE_CACHE_H
 
+/*
+ * This is the trim state of an extent or bitmap.
+ *
+ * BTRFS_TRIM_STATE_TRIMMING is special and used to maintain the state of a
+ * bitmap as we may need several trims to fully trim a single bitmap entry.
+ * This is reset should any free space other than trimmed space be added to the
+ * bitmap.
+ */
+enum btrfs_trim_state {
+	BTRFS_TRIM_STATE_UNTRIMMED,
+	BTRFS_TRIM_STATE_TRIMMED,
+	BTRFS_TRIM_STATE_TRIMMING,
+};
+
 struct btrfs_free_space {
 	struct rb_node offset_index;
 	u64 offset;
@@ -13,8 +27,21 @@ struct btrfs_free_space {
 	u64 max_extent_size;
 	unsigned long *bitmap;
 	struct list_head list;
+	enum btrfs_trim_state trim_state;
+	s32 bitmap_extents;
 };
 
+static inline bool btrfs_free_space_trimmed(struct btrfs_free_space *info)
+{
+	return (info->trim_state == BTRFS_TRIM_STATE_TRIMMED);
+}
+
+static inline bool btrfs_free_space_trimming_bitmap(
+					    struct btrfs_free_space *info)
+{
+	return (info->trim_state == BTRFS_TRIM_STATE_TRIMMING);
+}
+
 struct btrfs_free_space_ctl {
 	spinlock_t tree_lock;
 	struct rb_root free_space_offset;
@@ -24,6 +51,8 @@ struct btrfs_free_space_ctl {
 	int total_bitmaps;
 	int unit;
 	u64 start;
+	s32 discardable_extents[BTRFS_STAT_NR_ENTRIES];
+	s64 discardable_bytes[BTRFS_STAT_NR_ENTRIES];
 	const struct btrfs_free_space_op *op;
 	void *private;
 	struct mutex cache_writeout_mutex;
@@ -83,13 +112,17 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group);
 int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 			   struct btrfs_free_space_ctl *ctl,
-			   u64 bytenr, u64 size);
+			   u64 bytenr, u64 size,
+			   enum btrfs_trim_state trim_state);
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
+int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
+				       u64 bytenr, u64 size);
 int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 			    u64 bytenr, u64 size);
 void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl);
 void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group);
+bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size);
@@ -108,6 +141,12 @@ int btrfs_return_cluster_to_free_space(
 			       struct btrfs_free_cluster *cluster);
 int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen);
+int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group,
+				   u64 *trimmed, u64 start, u64 end, u64 minlen,
+				   bool async);
+int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
+				   u64 *trimmed, u64 start, u64 end, u64 minlen,
+				   u64 maxlen, bool async);
 
 /* Support functions for running our sanity tests */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS

fs/btrfs/inode-map.c

@@ -107,7 +107,7 @@ static int caching_kthread(void *data)
 
 		if (last != (u64)-1 && last + 1 != key.objectid) {
 			__btrfs_add_free_space(fs_info, ctl, last + 1,
-					       key.objectid - last - 1);
+					       key.objectid - last - 1, 0);
 			wake_up(&root->ino_cache_wait);
 		}
 
@@ -118,7 +118,7 @@ static int caching_kthread(void *data)
 
 	if (last < root->highest_objectid - 1) {
 		__btrfs_add_free_space(fs_info, ctl, last + 1,
-				       root->highest_objectid - last - 1);
+				       root->highest_objectid - last - 1, 0);
 	}
 
 	spin_lock(&root->ino_cache_lock);
@@ -175,7 +175,8 @@ static void start_caching(struct btrfs_root *root)
 	ret = btrfs_find_free_objectid(root, &objectid);
 	if (!ret && objectid <= BTRFS_LAST_FREE_OBJECTID) {
 		__btrfs_add_free_space(fs_info, ctl, objectid,
-				       BTRFS_LAST_FREE_OBJECTID - objectid + 1);
+				       BTRFS_LAST_FREE_OBJECTID - objectid + 1,
+				       0);
 		wake_up(&root->ino_cache_wait);
 	}
 
@@ -221,7 +222,7 @@ void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 		return;
 again:
 	if (root->ino_cache_state == BTRFS_CACHE_FINISHED) {
-		__btrfs_add_free_space(fs_info, pinned, objectid, 1);
+		__btrfs_add_free_space(fs_info, pinned, objectid, 1, 0);
 	} else {
 		down_write(&fs_info->commit_root_sem);
 		spin_lock(&root->ino_cache_lock);
@@ -234,7 +235,7 @@ void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 
 		start_caching(root);
 
-		__btrfs_add_free_space(fs_info, pinned, objectid, 1);
+		__btrfs_add_free_space(fs_info, pinned, objectid, 1, 0);
 
 		up_write(&fs_info->commit_root_sem);
 	}
@@ -281,7 +282,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		spin_unlock(rbroot_lock);
 		if (count)
 			__btrfs_add_free_space(root->fs_info, ctl,
-					       info->offset, count);
+					       info->offset, count, 0);
 		kmem_cache_free(btrfs_free_space_cachep, info);
 	}
 }

fs/btrfs/ioctl.c

@@ -1128,7 +1128,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
 
 		/* get the big lock and read metadata off disk */
 		lock_extent_bits(io_tree, start, end, &cached);
-		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
 		unlock_extent_cached(io_tree, start, end, &cached);
 
 		if (IS_ERR(em))

fs/btrfs/ordered-data.c

@@ -20,9 +20,9 @@ static struct kmem_cache *btrfs_ordered_extent_cache;
 
 static u64 entry_end(struct btrfs_ordered_extent *entry)
 {
-	if (entry->file_offset + entry->len < entry->file_offset)
+	if (entry->file_offset + entry->num_bytes < entry->file_offset)
 		return (u64)-1;
-	return entry->file_offset + entry->len;
+	return entry->file_offset + entry->num_bytes;
 }
 
 /* returns NULL if the insertion worked, or it returns the node it did find
@@ -52,14 +52,6 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 file_offset,
 	return NULL;
 }
 
-static void ordered_data_tree_panic(struct inode *inode, int errno,
-					       u64 offset)
-{
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	btrfs_panic(fs_info, errno,
-		    "Inconsistency in ordered tree at offset %llu", offset);
-}
-
 /*
  * look for a given offset in the tree, and if it can't be found return the
  * first lesser offset
@@ -120,7 +112,7 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 file_offset,
 static int offset_in_entry(struct btrfs_ordered_extent *entry, u64 file_offset)
 {
 	if (file_offset < entry->file_offset ||
-	    entry->file_offset + entry->len <= file_offset)
+	    entry->file_offset + entry->num_bytes <= file_offset)
 		return 0;
 	return 1;
 }
@@ -129,7 +121,7 @@ static int range_overlaps(struct btrfs_ordered_extent *entry, u64 file_offset,
 			  u64 len)
 {
 	if (file_offset + len <= entry->file_offset ||
-	    entry->file_offset + entry->len <= file_offset)
+	    entry->file_offset + entry->num_bytes <= file_offset)
 		return 0;
 	return 1;
 }
@@ -161,19 +153,14 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
 }
 
 /* allocate and add a new ordered_extent into the per-inode tree.
- * file_offset is the logical offset in the file
- *
- * start is the disk block number of an extent already reserved in the
- * extent allocation tree
- *
- * len is the length of the extent
  *
  * The tree is given a single reference on the ordered extent that was
  * inserted.
  */
 static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
-				      u64 start, u64 len, u64 disk_len,
-				      int type, int dio, int compress_type)
+				      u64 disk_bytenr, u64 num_bytes,
+				      u64 disk_num_bytes, int type, int dio,
+				      int compress_type)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -187,10 +174,10 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 		return -ENOMEM;
 
 	entry->file_offset = file_offset;
-	entry->start = start;
-	entry->len = len;
-	entry->disk_len = disk_len;
-	entry->bytes_left = len;
+	entry->disk_bytenr = disk_bytenr;
+	entry->num_bytes = num_bytes;
+	entry->disk_num_bytes = disk_num_bytes;
+	entry->bytes_left = num_bytes;
 	entry->inode = igrab(inode);
 	entry->compress_type = compress_type;
 	entry->truncated_len = (u64)-1;
@@ -198,7 +185,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 		set_bit(type, &entry->flags);
 
 	if (dio) {
-		percpu_counter_add_batch(&fs_info->dio_bytes, len,
+		percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes,
 					 fs_info->delalloc_batch);
 		set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
 	}
@@ -219,7 +206,9 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	node = tree_insert(&tree->tree, file_offset,
 			   &entry->rb_node);
 	if (node)
-		ordered_data_tree_panic(inode, -EEXIST, file_offset);
+		btrfs_panic(fs_info, -EEXIST,
+				"inconsistency in ordered tree at offset %llu",
+				file_offset);
 	spin_unlock_irq(&tree->lock);
 
 	spin_lock(&root->ordered_extent_lock);
@@ -247,27 +236,30 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 }
 
 int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
-			     u64 start, u64 len, u64 disk_len, int type)
+			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
+			     int type)
 {
-	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 0,
+	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
+					  num_bytes, disk_num_bytes, type, 0,
 					  BTRFS_COMPRESS_NONE);
 }
 
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
-				 u64 start, u64 len, u64 disk_len, int type)
+				 u64 disk_bytenr, u64 num_bytes,
+				 u64 disk_num_bytes, int type)
 {
-	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 1,
+	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
+					  num_bytes, disk_num_bytes, type, 1,
 					  BTRFS_COMPRESS_NONE);
 }
 
 int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
-				      u64 start, u64 len, u64 disk_len,
-				      int type, int compress_type)
+				      u64 disk_bytenr, u64 num_bytes,
+				      u64 disk_num_bytes, int type,
+				      int compress_type)
 {
-	return __btrfs_add_ordered_extent(inode, file_offset, start, len,
-					  disk_len, type, 0,
+	return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
+					  num_bytes, disk_num_bytes, type, 0,
 					  compress_type);
 }
 
@@ -328,8 +320,8 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 	}
 
 	dec_start = max(*file_offset, entry->file_offset);
-	dec_end = min(*file_offset + io_size, entry->file_offset +
-		      entry->len);
+	dec_end = min(*file_offset + io_size,
+		      entry->file_offset + entry->num_bytes);
 	*file_offset = dec_end;
 	if (dec_start > dec_end) {
 		btrfs_crit(fs_info, "bad ordering dec_start %llu end %llu",
@@ -471,10 +463,11 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	btrfs_mod_outstanding_extents(btrfs_inode, -1);
 	spin_unlock(&btrfs_inode->lock);
 	if (root != fs_info->tree_root)
-		btrfs_delalloc_release_metadata(btrfs_inode, entry->len, false);
+		btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,
+						false);
 
 	if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
-		percpu_counter_add_batch(&fs_info->dio_bytes, -entry->len,
+		percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes,
 					 fs_info->delalloc_batch);
 
 	tree = &btrfs_inode->ordered_tree;
@@ -534,8 +527,8 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 		ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
 					   root_extent_list);
 
-		if (range_end <= ordered->start ||
-		    ordered->start + ordered->disk_len <= range_start) {
+		if (range_end <= ordered->disk_bytenr ||
+		    ordered->disk_bytenr + ordered->disk_num_bytes <= range_start) {
 			list_move_tail(&ordered->root_extent_list, &skipped);
 			cond_resched_lock(&root->ordered_extent_lock);
 			continue;
@@ -619,7 +612,7 @@ void btrfs_start_ordered_extent(struct inode *inode,
 				       int wait)
 {
 	u64 start = entry->file_offset;
-	u64 end = start + entry->len - 1;
+	u64 end = start + entry->num_bytes - 1;
 
 	trace_btrfs_ordered_extent_start(inode, entry);
 
@@ -680,7 +673,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
-		if (ordered->file_offset + ordered->len <= start) {
+		if (ordered->file_offset + ordered->num_bytes <= start) {
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}

fs/btrfs/ordered-data.h

@@ -67,14 +67,13 @@ struct btrfs_ordered_extent {
 	/* logical offset in the file */
 	u64 file_offset;
 
-	/* disk byte number */
-	u64 start;
-
-	/* ram length of the extent in bytes */
-	u64 len;
-
-	/* extent length on disk */
-	u64 disk_len;
+	/*
+	 * These fields directly correspond to the same fields in
+	 * btrfs_file_extent_item.
+	 */
+	u64 disk_bytenr;
+	u64 num_bytes;
+	u64 disk_num_bytes;
 
 	/* number of bytes that still need writing */
 	u64 bytes_left;
@@ -161,12 +160,15 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 				   u64 *file_offset, u64 io_size,
 				   int uptodate);
 int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
-			     u64 start, u64 len, u64 disk_len, int type);
+			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
+			     int type);
 int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
-				 u64 start, u64 len, u64 disk_len, int type);
+				 u64 disk_bytenr, u64 num_bytes,
+				 u64 disk_num_bytes, int type);
 int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
-				      u64 start, u64 len, u64 disk_len,
-				      int type, int compress_type);
+				      u64 disk_bytenr, u64 num_bytes,
+				      u64 disk_num_bytes, int type,
+				      int compress_type);
 void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 			   struct btrfs_ordered_sum *sum);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,

fs/btrfs/print-tree.c

@@ -317,7 +317,7 @@ void btrfs_print_leaf(struct extent_buffer *l)
 			print_uuid_item(l, btrfs_item_ptr_offset(l, i),
 					btrfs_item_size_nr(l, i));
 			break;
-		};
+		}
 	}
 }
 

fs/btrfs/qgroup.c

@@ -1243,7 +1243,6 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
 	struct btrfs_qgroup_list *list;
@@ -1259,9 +1258,8 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 		return -ENOMEM;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	quota_root = fs_info->quota_root;
-	if (!quota_root) {
-		ret = -EINVAL;
+	if (!fs_info->quota_root) {
+		ret = -ENOTCONN;
 		goto out;
 	}
 	member = find_qgroup_rb(fs_info, src);
@@ -1307,7 +1305,6 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 				 u64 dst)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
 	struct btrfs_qgroup_list *list;
@@ -1320,9 +1317,8 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 	if (!tmp)
 		return -ENOMEM;
 
-	quota_root = fs_info->quota_root;
-	if (!quota_root) {
-		ret = -EINVAL;
+	if (!fs_info->quota_root) {
+		ret = -ENOTCONN;
 		goto out;
 	}
 
@@ -1387,11 +1383,11 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	quota_root = fs_info->quota_root;
-	if (!quota_root) {
-		ret = -EINVAL;
+	if (!fs_info->quota_root) {
+		ret = -ENOTCONN;
 		goto out;
 	}
+	quota_root = fs_info->quota_root;
 	qgroup = find_qgroup_rb(fs_info, qgroupid);
 	if (qgroup) {
 		ret = -EEXIST;
@@ -1416,15 +1412,13 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *list;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	quota_root = fs_info->quota_root;
-	if (!quota_root) {
-		ret = -EINVAL;
+	if (!fs_info->quota_root) {
+		ret = -ENOTCONN;
 		goto out;
 	}
 
@@ -1465,7 +1459,6 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
 	/* Sometimes we would want to clear the limit on this qgroup.
@@ -1475,9 +1468,8 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 	const u64 CLEAR_VALUE = -1;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	quota_root = fs_info->quota_root;
-	if (!quota_root) {
-		ret = -EINVAL;
+	if (!fs_info->quota_root) {
+		ret = -ENOTCONN;
 		goto out;
 	}
 
@@ -2582,10 +2574,9 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_root *quota_root = fs_info->quota_root;
 	int ret = 0;
 
-	if (!quota_root)
+	if (!fs_info->quota_root)
 		return ret;
 
 	spin_lock(&fs_info->qgroup_lock);
@@ -2879,7 +2870,6 @@ static bool qgroup_check_limits(struct btrfs_fs_info *fs_info,
 static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
 			  enum btrfs_qgroup_rsv_type type)
 {
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 ref_root = root->root_key.objectid;
@@ -2898,8 +2888,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
 		enforce = false;
 
 	spin_lock(&fs_info->qgroup_lock);
-	quota_root = fs_info->quota_root;
-	if (!quota_root)
+	if (!fs_info->quota_root)
 		goto out;
 
 	qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -2966,7 +2955,6 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type)
 {
-	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
@@ -2984,8 +2972,7 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 	}
 	spin_lock(&fs_info->qgroup_lock);
 
-	quota_root = fs_info->quota_root;
-	if (!quota_root)
+	if (!fs_info->quota_root)
 		goto out;
 
 	qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -3685,7 +3672,6 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
 				int num_bytes)
 {
-	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
@@ -3693,7 +3679,7 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
 
 	if (num_bytes == 0)
 		return;
-	if (!quota_root)
+	if (!fs_info->quota_root)
 		return;
 
 	spin_lock(&fs_info->qgroup_lock);

fs/btrfs/relocation.c

@@ -4332,6 +4332,15 @@ static void describe_relocation(struct btrfs_fs_info *fs_info,
 		   block_group->start, buf);
 }
 
+static const char *stage_to_string(int stage)
+{
+	if (stage == MOVE_DATA_EXTENTS)
+		return "move data extents";
+	if (stage == UPDATE_DATA_PTRS)
+		return "update data pointers";
+	return "unknown";
+}
+
 /*
  * function to relocate all extents in a block group.
  */
@@ -4406,12 +4415,15 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 				 rc->block_group->length);
 
 	while (1) {
+		int finishes_stage;
+
 		mutex_lock(&fs_info->cleaner_mutex);
 		ret = relocate_block_group(rc);
 		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0)
 			err = ret;
 
+		finishes_stage = rc->stage;
 		/*
 		 * We may have gotten ENOSPC after we already dirtied some
 		 * extents.  If writeout happens while we're relocating a
@@ -4437,8 +4449,8 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 		if (rc->extents_found == 0)
 			break;
 
-		btrfs_info(fs_info, "found %llu extents", rc->extents_found);
-
+		btrfs_info(fs_info, "found %llu extents, stage: %s",
+			   rc->extents_found, stage_to_string(finishes_stage));
 	}
 
 	WARN_ON(rc->block_group->pinned > 0);
@@ -4656,7 +4668,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 	LIST_HEAD(list);
 
 	ordered = btrfs_lookup_ordered_extent(inode, file_pos);
-	BUG_ON(ordered->file_offset != file_pos || ordered->len != len);
+	BUG_ON(ordered->file_offset != file_pos || ordered->num_bytes != len);
 
 	disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt;
 	ret = btrfs_lookup_csums_range(fs_info->csum_root, disk_bytenr,
@@ -4680,7 +4692,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 		 * disk_len vs real len like with real inodes since it's all
 		 * disk length.
 		 */
-		new_bytenr = ordered->start + (sums->bytenr - disk_bytenr);
+		new_bytenr = ordered->disk_bytenr + sums->bytenr - disk_bytenr;
 		sums->bytenr = new_bytenr;
 
 		btrfs_add_ordered_sum(ordered, sums);

fs/btrfs/scrub.c

@@ -8,6 +8,7 @@
 #include <linux/sched/mm.h>
 #include <crypto/hash.h>
 #include "ctree.h"
+#include "discard.h"
 #include "volumes.h"
 #include "disk-io.h"
 #include "ordered-data.h"
@@ -3682,7 +3683,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    cache->used == 0) {
 			spin_unlock(&cache->lock);
-			btrfs_mark_bg_unused(cache);
+			if (btrfs_test_opt(fs_info, DISCARD_ASYNC))
+				btrfs_discard_queue_work(&fs_info->discard_ctl,
+							 cache);
+			else
+				btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}

fs/btrfs/space-info.c

@@ -161,8 +161,7 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
 
 static int can_overcommit(struct btrfs_fs_info *fs_info,
 			  struct btrfs_space_info *space_info, u64 bytes,
-			  enum btrfs_reserve_flush_enum flush,
-			  bool system_chunk)
+			  enum btrfs_reserve_flush_enum flush)
 {
 	u64 profile;
 	u64 avail;
@@ -173,7 +172,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
 		return 0;
 
-	if (system_chunk)
+	if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		profile = btrfs_system_alloc_profile(fs_info);
 	else
 		profile = btrfs_metadata_alloc_profile(fs_info);
@@ -227,8 +226,7 @@ void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 
 		/* Check and see if our ticket can be satisified now. */
 		if ((used + ticket->bytes <= space_info->total_bytes) ||
-		    can_overcommit(fs_info, space_info, ticket->bytes, flush,
-				   false)) {
+		    can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
@@ -626,8 +624,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 
 static inline u64
 btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
-				 struct btrfs_space_info *space_info,
-				 bool system_chunk)
+				 struct btrfs_space_info *space_info)
 {
 	struct reserve_ticket *ticket;
 	u64 used;
@@ -643,13 +640,12 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
 	if (can_overcommit(fs_info, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
+			   BTRFS_RESERVE_FLUSH_ALL))
 		return 0;
 
 	used = btrfs_space_info_used(space_info, true);
 
-	if (can_overcommit(fs_info, space_info, SZ_1M,
-			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
+	if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -665,7 +661,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 
 static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 					struct btrfs_space_info *space_info,
-					u64 used, bool system_chunk)
+					u64 used)
 {
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
@@ -673,8 +669,7 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
 	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
-	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-					      system_chunk))
+	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info))
 		return 0;
 
 	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
@@ -765,8 +760,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 	space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-						      false);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info);
 	if (!to_reclaim) {
 		space_info->flush = 0;
 		spin_unlock(&space_info->lock);
@@ -785,8 +779,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 			return;
 		}
 		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
-							      space_info,
-							      false);
+							      space_info);
 		if (last_tickets_id == space_info->tickets_id) {
 			flush_state++;
 		} else {
@@ -858,8 +851,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	int flush_state;
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
-						      false);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info);
 	if (!to_reclaim) {
 		spin_unlock(&space_info->lock);
 		return;
@@ -990,8 +982,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
 static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info,
 				    u64 orig_bytes,
-				    enum btrfs_reserve_flush_enum flush,
-				    bool system_chunk)
+				    enum btrfs_reserve_flush_enum flush)
 {
 	struct reserve_ticket ticket;
 	u64 used;
@@ -1013,8 +1004,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 */
 	if (!pending_tickets &&
 	    ((used + orig_bytes <= space_info->total_bytes) ||
-	     can_overcommit(fs_info, space_info, orig_bytes, flush,
-			   system_chunk))) {
+	     can_overcommit(fs_info, space_info, orig_bytes, flush))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
 		ret = 0;
@@ -1054,8 +1044,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 		 * the async reclaim as we will panic.
 		 */
 		if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) &&
-		    need_do_async_reclaim(fs_info, space_info,
-					  used, system_chunk) &&
+		    need_do_async_reclaim(fs_info, space_info, used) &&
 		    !work_busy(&fs_info->async_reclaim_work)) {
 			trace_btrfs_trigger_flush(fs_info, space_info->flags,
 						  orig_bytes, flush, "preempt");
@@ -1092,10 +1081,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	int ret;
-	bool system_chunk = (root == fs_info->chunk_root);
 
 	ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info,
-				       orig_bytes, flush, system_chunk);
+				       orig_bytes, flush);
 	if (ret == -ENOSPC &&
 	    unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
 		if (block_rsv != global_rsv &&

fs/btrfs/super.c

@@ -46,6 +46,7 @@
 #include "sysfs.h"
 #include "tests/btrfs-tests.h"
 #include "block-group.h"
+#include "discard.h"
 
 #include "qgroup.h"
 #define CREATE_TRACE_POINTS
@@ -146,6 +147,8 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function
 	if (sb_rdonly(sb))
 		return;
 
+	btrfs_discard_stop(fs_info);
+
 	/* btrfs handle error by forcing the filesystem readonly */
 	sb->s_flags |= SB_RDONLY;
 	btrfs_info(fs_info, "forced readonly");
@@ -313,6 +316,7 @@ enum {
 	Opt_datasum, Opt_nodatasum,
 	Opt_defrag, Opt_nodefrag,
 	Opt_discard, Opt_nodiscard,
+	Opt_discard_mode,
 	Opt_nologreplay,
 	Opt_norecovery,
 	Opt_ratio,
@@ -375,6 +379,7 @@ static const match_table_t tokens = {
 	{Opt_defrag, "autodefrag"},
 	{Opt_nodefrag, "noautodefrag"},
 	{Opt_discard, "discard"},
+	{Opt_discard_mode, "discard=%s"},
 	{Opt_nodiscard, "nodiscard"},
 	{Opt_nologreplay, "nologreplay"},
 	{Opt_norecovery, "norecovery"},
@@ -695,12 +700,26 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 				   info->metadata_ratio);
 			break;
 		case Opt_discard:
-			btrfs_set_and_info(info, DISCARD,
-					   "turning on discard");
+		case Opt_discard_mode:
+			if (token == Opt_discard ||
+			    strcmp(args[0].from, "sync") == 0) {
+				btrfs_clear_opt(info->mount_opt, DISCARD_ASYNC);
+				btrfs_set_and_info(info, DISCARD_SYNC,
+						   "turning on sync discard");
+			} else if (strcmp(args[0].from, "async") == 0) {
+				btrfs_clear_opt(info->mount_opt, DISCARD_SYNC);
+				btrfs_set_and_info(info, DISCARD_ASYNC,
+						   "turning on async discard");
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
 			break;
 		case Opt_nodiscard:
-			btrfs_clear_and_info(info, DISCARD,
+			btrfs_clear_and_info(info, DISCARD_SYNC,
 					     "turning off discard");
+			btrfs_clear_and_info(info, DISCARD_ASYNC,
+					     "turning off async discard");
 			break;
 		case Opt_space_cache:
 		case Opt_space_cache_version:
@@ -1322,8 +1341,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",nologreplay");
 	if (btrfs_test_opt(info, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
-	if (btrfs_test_opt(info, DISCARD))
+	if (btrfs_test_opt(info, DISCARD_SYNC))
 		seq_puts(seq, ",discard");
+	if (btrfs_test_opt(info, DISCARD_ASYNC))
+		seq_puts(seq, ",discard=async");
 	if (!(info->sb->s_flags & SB_POSIXACL))
 		seq_puts(seq, ",noacl");
 	if (btrfs_test_opt(info, SPACE_CACHE))
@@ -1713,6 +1734,14 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
 		btrfs_cleanup_defrag_inodes(fs_info);
 	}
 
+	/* If we toggled discard async */
+	if (!btrfs_raw_test_opt(old_opts, DISCARD_ASYNC) &&
+	    btrfs_test_opt(fs_info, DISCARD_ASYNC))
+		btrfs_discard_resume(fs_info);
+	else if (btrfs_raw_test_opt(old_opts, DISCARD_ASYNC) &&
+		 !btrfs_test_opt(fs_info, DISCARD_ASYNC))
+		btrfs_discard_cleanup(fs_info);
+
 	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 }
 
@@ -1760,6 +1789,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		 */
 		cancel_work_sync(&fs_info->async_reclaim_work);
 
+		btrfs_discard_cleanup(fs_info);
+
 		/* wait for the uuid_scan task to finish */
 		down(&fs_info->uuid_tree_rescan_sem);
 		/* avoid complains from lockdep et al. */

fs/btrfs/sysfs.h

@@ -18,9 +18,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 		struct btrfs_device *one_device);
 int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
                 struct btrfs_device *one_device);
-int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
-				struct kobject *parent);
-int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
+int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices,
 				    const u8 *fsid);
@@ -36,5 +34,6 @@ void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache);
 int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info);
 void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
+void btrfs_sysfs_update_devid(struct btrfs_device *device);
 
 #endif

fs/btrfs/tests/btrfs-tests.c

@@ -86,6 +86,27 @@ static void btrfs_destroy_test_fs(void)
 	unregister_filesystem(&test_type);
 }
 
+struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_device *dev;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	extent_io_tree_init(NULL, &dev->alloc_state, 0, NULL);
+	INIT_LIST_HEAD(&dev->dev_list);
+	list_add(&dev->dev_list, &fs_info->fs_devices->devices);
+
+	return dev;
+}
+
+static void btrfs_free_dummy_device(struct btrfs_device *dev)
+{
+	extent_io_tree_release(&dev->alloc_state);
+	kfree(dev);
+}
+
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 {
 	struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
@@ -132,12 +153,14 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 	INIT_LIST_HEAD(&fs_info->dirty_qgroups);
 	INIT_LIST_HEAD(&fs_info->dead_roots);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
+	INIT_LIST_HEAD(&fs_info->fs_devices->devices);
 	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
 	extent_io_tree_init(fs_info, &fs_info->freed_extents[0],
 			    IO_TREE_FS_INFO_FREED_EXTENTS0, NULL);
 	extent_io_tree_init(fs_info, &fs_info->freed_extents[1],
 			    IO_TREE_FS_INFO_FREED_EXTENTS1, NULL);
+	extent_map_tree_init(&fs_info->mapping_tree);
 	fs_info->pinned_extents = &fs_info->freed_extents[0];
 	set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
 
@@ -150,6 +173,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 {
 	struct radix_tree_iter iter;
 	void **slot;
+	struct btrfs_device *dev, *tmp;
 
 	if (!fs_info)
 		return;
@@ -180,6 +204,11 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	}
 	spin_unlock(&fs_info->buffer_lock);
 
+	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices,
+				 dev_list) {
+		btrfs_free_dummy_device(dev);
+	}
 	btrfs_free_qgroup_config(fs_info);
 	btrfs_free_fs_roots(fs_info);
 	cleanup_srcu_struct(&fs_info->subvol_srcu);

fs/btrfs/tests/btrfs-tests.h

@@ -46,6 +46,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, unsigned long lengt
 void btrfs_free_dummy_block_group(struct btrfs_block_group *cache);
 void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info);
+struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info);
 #else
 static inline int btrfs_run_sanity_tests(void)
 {

fs/btrfs/transaction.c

@@ -147,13 +147,14 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 	}
 }
 
-static noinline void switch_commit_roots(struct btrfs_transaction *trans)
+static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root, *tmp;
 
 	down_write(&fs_info->commit_root_sem);
-	list_for_each_entry_safe(root, tmp, &trans->switch_commits,
+	list_for_each_entry_safe(root, tmp, &cur_trans->switch_commits,
 				 dirty_list) {
 		list_del_init(&root->dirty_list);
 		free_extent_buffer(root->commit_root);
@@ -165,16 +166,17 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans)
 	}
 
 	/* We can free old roots now. */
-	spin_lock(&trans->dropped_roots_lock);
-	while (!list_empty(&trans->dropped_roots)) {
-		root = list_first_entry(&trans->dropped_roots,
+	spin_lock(&cur_trans->dropped_roots_lock);
+	while (!list_empty(&cur_trans->dropped_roots)) {
+		root = list_first_entry(&cur_trans->dropped_roots,
 					struct btrfs_root, root_list);
 		list_del_init(&root->root_list);
-		spin_unlock(&trans->dropped_roots_lock);
+		spin_unlock(&cur_trans->dropped_roots_lock);
+		btrfs_free_log(trans, root);
 		btrfs_drop_and_free_fs_root(fs_info, root);
-		spin_lock(&trans->dropped_roots_lock);
+		spin_lock(&cur_trans->dropped_roots_lock);
 	}
-	spin_unlock(&trans->dropped_roots_lock);
+	spin_unlock(&cur_trans->dropped_roots_lock);
 	up_write(&fs_info->commit_root_sem);
 }
 
@@ -1421,7 +1423,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	ret = commit_cowonly_roots(trans);
 	if (ret)
 		goto out;
-	switch_commit_roots(trans->transaction);
+	switch_commit_roots(trans);
 	ret = btrfs_write_and_wait_transaction(trans);
 	if (ret)
 		btrfs_handle_fs_error(fs_info, ret,
@@ -2013,6 +2015,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	ASSERT(refcount_read(&trans->use_count) == 1);
 
+	/*
+	 * Some places just start a transaction to commit it.  We need to make
+	 * sure that if this commit fails that the abort code actually marks the
+	 * transaction as failed, so set trans->dirty to make the abort code do
+	 * the right thing.
+	 */
+	trans->dirty = true;
+
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
@@ -2301,7 +2311,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	list_add_tail(&fs_info->chunk_root->dirty_list,
 		      &cur_trans->switch_commits);
 
-	switch_commit_roots(cur_trans);
+	switch_commit_roots(trans);
 
 	ASSERT(list_empty(&cur_trans->dirty_bgs));
 	ASSERT(list_empty(&cur_trans->io_bgs));

include/trace/events/btrfs.h

@@ -496,9 +496,9 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
 		__entry->ino 		= btrfs_ino(BTRFS_I(inode));
 		__entry->file_offset	= ordered->file_offset;
-		__entry->start		= ordered->start;
-		__entry->len		= ordered->len;
-		__entry->disk_len	= ordered->disk_len;
+		__entry->start		= ordered->disk_bytenr;
+		__entry->len		= ordered->num_bytes;
+		__entry->disk_len	= ordered->disk_num_bytes;
 		__entry->bytes_left	= ordered->bytes_left;
 		__entry->flags		= ordered->flags;
 		__entry->compress_type	= ordered->compress_type;